Triple

T15145525
Position Surface form Disambiguated ID Type / Status
Subject Orange S.A. E361793 entity
Predicate subsidiary P258 FINISHED
Object Orange Polska E634642 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Orange Polska | Statement: [Orange S.A., subsidiary, Orange Polska]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orange Polska
Context triple: [Orange S.A., subsidiary, Orange Polska]
  • A. Orange Polska chosen
    Orange Polska is one of Poland’s largest telecommunications companies, providing nationwide fixed and mobile phone, internet, and TV services.
  • B. Orlen
    Orlen is a district of the town of Taunusstein in the Rheingau-Taunus-Kreis region of Hesse, Germany.
  • C. UPC Polska
    UPC Polska is a leading Polish telecommunications company that provides broadband internet, digital television, and telephone services to households and businesses across Poland.
  • D. SKM Warsaw
    SKM Warsaw is a suburban rapid rail service operating within the Warsaw metropolitan area, providing fast commuter connections that complement the city's broader public transport system.
  • E. TVP Polonia
    TVP Polonia is an international Polish television channel aimed primarily at the Polish diaspora, broadcasting a selection of programs from Poland’s public broadcaster.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d85a0759908190b8a051d2e2a1cbe6 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005c71b688190b2e8ccfdf4db9037 completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69febff02e648190bd10f04a374da227 completed May 9, 2026, 5:02 a.m.
Created at: April 10, 2026, 3:07 a.m.